Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal principles and arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "way" or similar words

    np_acts-logits-general · gemini-2.0-flash

    manner or way

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Meksiku
    -0.70
    ⓧ
    -0.58
    ArrowToggle
    -0.56
    dius
    -0.51
     éduc
    -0.49
     Perfon
    -0.48
    Gweler
    -0.48
    KeyId
    -0.47
    lect
    -0.47
     Brod
    -0.47
    POSITIVE LOGITS
     way
    1.53
     differently
    1.32
     ways
    1.23
     WAY
    1.23
     manner
    1.20
     Way
    1.18
    Way
    1.16
    way
    1.06
     Ways
    1.03
     WAYS
    0.97
    Act Density 0.528%

    No Known Activations